2017/12/11 by Matthias Meyer, Meyer, Matthias, Jan Beutel +3
Computer Science · #Artificial intelligence #Audio analyzer #Audio signal #Audio signal processing #Computer Vision and Pattern Recognition (cs.CV) #Computer science #FOS: Computer and information sciences #Feature (linguistics) #Feature learning #Linguistics #Music and Audio Processing #Pattern recognition (psychology) #Speech Recognition and Synthesis #Speech and Audio Processing #Speech coding #Speech recognition #Unsupervised learning #cs.CV
paper · pdf · doi:10.48550/arxiv.1712.03835
Presented at the 5th International Conference on Learning Representations (ICLR) 2017, Workshop Track, Toulon, France
arxiv created 2017/12/11 · openalex publication_date 2017/12/11 · arxiv updated 2017/12/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Identifying acoustic events from a continuously streaming audio source is of interest for many applications including environmental monitoring for basic research. In this scenario neither different event classes are known nor what distinguishes one class from another. Therefore, an unsupervised feature learning method for exploration of audio data is presented in this paper. It incorporates the two following novel contributions: First, an audio frame predictor based on a Convolutional LSTM autoencoder is demonstrated, which is used for unsupervised feature extraction. Second, a training method for autoencoders is presented, which leads to distinct features by amplifying event similarities. In comparison to standard approaches, the features extracted from the audio frame predictor trained with the novel approach show 13 % better results when used with a classifier and 36 % better results when used for clustering.